© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 40007
    Prev
    Next
    INDEX
    Explanations

    .com domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ø©
    -0.12
    اÙĭ
    -0.09
    ive
    -0.08
    able
    -0.08
    å¦Ĥçİī
    -0.08
    æĢ§åľ°
    -0.08
    اÙĨØ©
    -0.08
    :],
    -0.08
    ungs
    -0.08
    ment
    -0.08
    POSITIVE LOGITS
    .au
    0.17
    .ua
    0.11
    .uk
    0.09
    缸è¾ħ缸æĪIJ
    0.08
    merce
    0.07
    .br
    0.07
    .cn
    0.07
    .mx
    0.07
    å¿ĺæĢĢ
    0.07
    /cgi
    0.07
    Activations Density 0.210%

    No Known Activations